The latest articles on DEV Community by Moises Moreno (@moiseshack02). https://dev.to/moiseshack02 https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https:%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F4209255%2F5479567e-51bd-4601-8d51-94c5bba0734f.jpg https://dev.to/moiseshack02 en Moises Moreno Mon, 26 Oct 2026 18:28:14 +0000 https://dev.to/moiseshack02/why-im-building-an-engineering-control-plane-for-ai-assisted-development-2hhd https://dev.to/moiseshack02/why-im-building-an-engineering-control-plane-for-ai-assisted-development-2hhd <h1> Why I'm Building an Engineering Control Plane for AI-Assisted Development </h1> <p>AI coding tools are becoming increasingly capable. They can generate code, analyze repositories, run tests, and help developers move faster.</p> <p>But as AI-assisted development grows, I keep coming back to a different question:</p> <p><strong>How do we engineer the system around the AI—not just the code it produces?</strong></p> <p>That question is one of the reasons I'm building <a href="https://github.com/SHEMASOFT/SYSTEM-ENGINEERING" rel="noopener noreferrer">SYSTEM-ENGINEERING</a>, an open-source project exploring the idea of an <strong>Engineering Control Plane for AI-assisted development</strong>.</p> <h2> The problem I'm exploring </h2> <p>Adding more agents or connecting more tools does not automatically create a reliable engineering workflow.</p> <p>A project also needs structure around the work:</p> <ul> <li> <strong>Orchestration:</strong> How should tasks be coordinated across specialized agents?</li> <li> <strong>Policies and contracts:</strong> How do we define what an agent can do, what it must respect, and when it should stop?</li> <li> <strong>Validation:</strong> How can we verify results instead of relying exclusively on an agent's claims?</li> <li> <strong>Memory and continuity:</strong> How can a project preserve relevant decisions and context across sessions?</li> <li> <strong>Project boundaries:</strong> How can shared engineering infrastructure support multiple projects without hardcoding project-specific assumptions?</li> </ul> <p>These are architectural questions, not just prompt-engineering questions.</p> <p>I'm interested in exploring whether these concerns can be addressed through a reusable engineering layer instead of being scattered across individual prompts, scripts, and tools.</p> <h2> What is SYSTEM-ENGINEERING? </h2> <p>SYSTEM-ENGINEERING is my open-source effort to explore that engineering layer.</p> <p>The project focuses on the infrastructure and workflows surrounding AI-assisted software development: orchestration, explicit policies, validation, persistent context, and project continuity.</p> <p>The goal is not to claim that AI-generated software can be made automatically reliable. The goal is to build better mechanisms for controlling, validating, and maintaining the process.</p> <p>There are still architectural choices to evaluate, limitations to uncover, and parts that need real-world testing. I want the project to evolve through evidence and technical feedback rather than assumptions.</p> <h2> What I want to learn from the community </h2> <p>I'm looking for developers who are willing to examine the project critically.</p> <p>In particular, I'd appreciate feedback on:</p> <ol> <li> <strong>Architecture:</strong> Does the control-plane approach provide a useful separation of concerns, or does it introduce unnecessary complexity?</li> <li> <strong>Agent orchestration:</strong> What should be handled by the orchestration layer, and what should remain native to the underlying coding tools?</li> <li> <strong>Reliability:</strong> Which validation mechanisms are essential? Where should the system stop and ask for human intervention?</li> <li> <strong>Memory and continuity:</strong> What information should persist between sessions, and how can stale or conflicting context be handled?</li> <li> <strong>Developer experience:</strong> Is the project understandable, portable, and practical to install and extend?</li> </ol> <p>I welcome bug reports, alternative designs, constructive criticism, and contributions. If you disagree with the architecture, explaining why would be just as valuable as suggesting an improvement.</p> <h2> Help shape the project </h2> <p>Repository: <a href="https://github.com/SHEMASOFT/SYSTEM-ENGINEERING" rel="noopener noreferrer">github.com/SHEMASOFT/SYSTEM-ENGINEERING</a></p> <p>If you're interested, start by exploring the repository and its documentation. Try what is relevant to your environment, report what breaks, and tell me what you would design differently.</p> <p>I'm especially interested in feedback grounded in actual testing, reproducible issues, and concrete architectural trade-offs.</p> <p>This is an ongoing open-source engineering effort, not a claim that every problem has already been solved.</p> <p><strong>What do you think is the biggest missing layer in today's AI-assisted development workflows: orchestration, validation, memory, policy enforcement, or something else entirely?</strong></p> <p>I'd like to hear your perspective.</p> ai opensource softwareengineering devtools Moises Moreno Mon, 26 Oct 2026 17:12:31 +0000 https://dev.to/moiseshack02/-bg4 https://dev.to/moiseshack02/-bg4